© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14659
    Prev
    Next
    INDEX
    Explanations

    titles of academic publications, locations, and URLs

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.54
    KURZBESCHREIBUNG
    -0.51
     Kỳ
    -0.50
     eating
    -0.50
    urka
    -0.48
    GEBURTSDATUM
    -0.48
     valami
    -0.47
    OrEqualTo
    -0.47
    flare
    -0.47
     rup
    -0.47
    POSITIVE LOGITS
     StringTokenizer
    0.58
     desglose
    0.55
    BagConstraints
    0.54
     eventdata
    0.53
    resave
    0.49
    esgue
    0.49
    IGraphics
    0.49
     málaga
    0.49
     hObject
    0.47
     bogotá
    0.47
    Activations Density 15.012%

    No Known Activations